© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83091
    Prev
    Next
    INDEX
    Explanations

    HTML table structure elements and related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equally
    -0.06
     Cort
    -0.06
    lot
    -0.06
    urm
    -0.06
    igham
    -0.06
    erchant
    -0.05
     parc
    -0.05
    â
    -0.05
    atron
    -0.05
    ÃĤ
    -0.05
    POSITIVE LOGITS
    åĿ¡
    0.07
    ames
    0.07
    omanip
    0.07
    -thumb
    0.07
    Argb
    0.07
    xac
    0.07
     ydk
    0.07
    ĶåĽŀ
    0.07
    ROUP
    0.07
    AME
    0.07
    Activations Density 0.050%

    No Known Activations